CSpace  > 系统科学研究所
An Empirical Feasibility Study of Societal Risk Classification Toward BBS Posts
Chen, Jindong1,4; Zhou, Xiaoji2; Tang, Xijin3,5
2018-12-01
Source PublicationJOURNAL OF SYSTEMS SCIENCE AND SYSTEMS ENGINEERING
ISSN1004-3756
Volume27Issue:6Pages:709-726
AbstractSocietal risk classification is the fundamental issue for online societal risk monitoring. To show the challenge and feasibility of societal risk classification toward BBS posts, an empirical analysis is implemented in this paper. Through effectiveness analysis, Support Vector Machine based on Bag-Of-Words (BOW-SVM) is adopted for challenge validation, and the distributed document embeddings of BBS posts generated by Paragraph Vector are applied to feasibility study. Based on BOW-SVM, cross-validations of BBS posts labeled by different groups and annotators are conducted. The big fluctuation of cross-validation results indicates the differences of individual risk perceptions, which brings more challenges to societal risk classification. Furthermore, based on the distributed document embeddings of BBS posts, the pairwise similarities of more than 300 thousands BBS posts from different societal risk categories are compared. The higher similarities of BBS posts in the same societal risk category reveal that BBS posts in the same societal risk category share more features than BBS posts in different categories, which manifests the feasibility of societal risk classification of BBS posts, and also reflects the possibility to improve the performance of societal risk monitoring.
KeywordSocietal risk classification Tianya Forum cross validation pairwise similarity individual risk perception
DOI10.1007/s11518-018-5372-x
Language英语
Funding ProjectNational Natural Science Foundation of China[71601023] ; National Natural Science Foundation of China[61473284] ; National Natural Science Foundation of China[71731002] ; National Natural Science Foundation of China[L1624049] ; Supplementary and Supportive Project for Teachers at Beijing Information Science and Technology University (2018-2020)[5029011103] ; National Key R&D Program of China[2017YFB1400500]
WOS Research AreaOperations Research & Management Science
WOS SubjectOperations Research & Management Science
WOS IDWOS:000451863100001
PublisherSPRINGER HEIDELBERG
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.amss.ac.cn/handle/2S8OKBNM/31781
Collection系统科学研究所
Affiliation1.Beijing Informat Sci & Technol Univ, Sch Econ & Management, Beijing 100192, Peoples R China
2.China Acad Aerosp Syst Sci & Engn, Beijing 100048, Peoples R China
3.Chinese Acad Sci, Acad Math & Syst Sci, Beijing 100190, Peoples R China
4.Beijing Key Lab Green Dev Decis Based Big Data, Beijing 100192, Peoples R China
5.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
Recommended Citation
GB/T 7714
Chen, Jindong,Zhou, Xiaoji,Tang, Xijin. An Empirical Feasibility Study of Societal Risk Classification Toward BBS Posts[J]. JOURNAL OF SYSTEMS SCIENCE AND SYSTEMS ENGINEERING,2018,27(6):709-726.
APA Chen, Jindong,Zhou, Xiaoji,&Tang, Xijin.(2018).An Empirical Feasibility Study of Societal Risk Classification Toward BBS Posts.JOURNAL OF SYSTEMS SCIENCE AND SYSTEMS ENGINEERING,27(6),709-726.
MLA Chen, Jindong,et al."An Empirical Feasibility Study of Societal Risk Classification Toward BBS Posts".JOURNAL OF SYSTEMS SCIENCE AND SYSTEMS ENGINEERING 27.6(2018):709-726.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Chen, Jindong]'s Articles
[Zhou, Xiaoji]'s Articles
[Tang, Xijin]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chen, Jindong]'s Articles
[Zhou, Xiaoji]'s Articles
[Tang, Xijin]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chen, Jindong]'s Articles
[Zhou, Xiaoji]'s Articles
[Tang, Xijin]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.